From b82e384c7bb9a19036b4daf58fa216df7cd48aa0 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 31 Oct 2011 10:56:32 -0400 Subject: ext4: optimize locking for end_io extent conversion Now that we are doing the locking correctly, we need to grab the i_completed_io_lock() twice per end_io. We can clean this up by removing the structure from the i_complted_io_list, and use this as the locking mechanism to prevent ext4_flush_completed_IO() racing against ext4_end_io_work(), instead of clearing the EXT4_IO_END_UNWRITTEN in io->flag. In addition, if the ext4_convert_unwritten_extents() returns an error, we no longer keep the end_io structure on the linked list. This doesn't help, because it tends to lock up the file system and wedges the system. That's one way to call attention to the problem, but it doesn't help the overall robustness of the system. Signed-off-by: "Theodore Ts'o" --- fs/ext4/page-io.c | 37 +++++++++++-------------------------- 1 file changed, 11 insertions(+), 26 deletions(-) (limited to 'fs/ext4/page-io.c') diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 4fa1d709b604..9eebf44646f6 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -99,28 +99,21 @@ int ext4_end_io_nolock(ext4_io_end_t *io) "list->prev 0x%p\n", io, inode->i_ino, io->list.next, io->list.prev); - if (!(io->flag & EXT4_IO_END_UNWRITTEN)) - return ret; - ret = ext4_convert_unwritten_extents(inode, offset, size); if (ret < 0) { - printk(KERN_EMERG "%s: failed to convert unwritten " - "extents to written extents, error is %d " - "io is still on inode %lu aio dio list\n", - __func__, ret, inode->i_ino); - return ret; + ext4_msg(inode->i_sb, KERN_EMERG, + "failed to convert unwritten extents to written " + "extents -- potential data loss! " + "(inode %lu, offset %llu, size %zd, error %d)", + inode->i_ino, offset, size, ret); } if (io->iocb) aio_complete(io->iocb, io->result, 0); - /* clear the DIO AIO unwritten flag */ - if (io->flag & EXT4_IO_END_UNWRITTEN) { - io->flag &= ~EXT4_IO_END_UNWRITTEN; - /* Wake up anyone waiting on unwritten extent conversion */ - if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten)) - wake_up_all(ext4_ioend_wq(io->inode)); - } + /* Wake up anyone waiting on unwritten extent conversion */ + if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten)) + wake_up_all(ext4_ioend_wq(io->inode)); return ret; } @@ -133,16 +126,15 @@ static void ext4_end_io_work(struct work_struct *work) struct inode *inode = io->inode; struct ext4_inode_info *ei = EXT4_I(inode); unsigned long flags; - int ret; spin_lock_irqsave(&ei->i_completed_io_lock, flags); if (list_empty(&io->list)) { spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); goto free; } - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); if (!mutex_trylock(&inode->i_mutex)) { + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); /* * Requeue the work instead of waiting so that the work * items queued after this can be processed. @@ -159,16 +151,9 @@ static void ext4_end_io_work(struct work_struct *work) io->flag |= EXT4_IO_END_QUEUED; return; } - ret = ext4_end_io_nolock(io); - if (ret < 0) { - mutex_unlock(&inode->i_mutex); - return; - } - - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - if (!list_empty(&io->list)) - list_del_init(&io->list); + list_del_init(&io->list); spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + (void) ext4_end_io_nolock(io); mutex_unlock(&inode->i_mutex); free: ext4_free_io_end(io); -- cgit v1.2.2